def __clusterize(self, files_faces, debug_out_folder=None):
self.__start_stage(len(files_faces))
encs = []
indexes = list(range(len(files_faces)))
random.shuffle(indexes)
for i in indexes:
for j in range(len(files_faces[i]['faces'])):
encs.append(dlib.vector(
files_faces[i]['faces'][j]['encoding']))
labels = dlib.chinese_whispers_clustering(
encs, self.__threshold_clusterize)
labels = self.__reassign_by_count(labels)
lnum = 0
for i in indexes:
if self.__step_stage():
break
for j in range(len(files_faces[i]['faces'])):
files_faces[i]['faces'][j]['name'] = \
'unknown_{:05d}'.format(labels[lnum])
lnum += 1
if debug_out_folder:
filename = files_faces[i]['filename']
media = tools.load_media(filename,
self.__max_size,
self.__max_video_frames,
self.__video_frames_step)
debug_out_file_name = self.__extract_filename(filename)
self.__save_debug_images(
files_faces[i]['faces'], media,
debug_out_folder, debug_out_file_name)
self.__end_stage()
def __save_faces(self, files_faces, debug_out_folder):
for ff in files_faces:
if self.__step_stage():
break
filename = ff['filename']
log.info(f"save faces from image: {filename}")
media = tools.load_media(filename,
self.__max_size,
self.__max_video_frames,
self.__video_frames_step)
debug_out_file_name = self.__extract_filename(filename)
is_video = tools.get_low_ext(filename) in tools.VIDEO_EXTS
self.__save_debug_images(
ff['faces'], media,
debug_out_folder, debug_out_file_name, is_video=is_video)
self.__step_stage_face(len(ff['faces']))
self.__end_stage()
def get_faces_by_face(self, filename, debug_out_folder,
remove_file=False):
if self.__init_stage('get_faces_by_face', locals()):
return
image = tools.LazyImage(filename, self.__max_size)
encoded_faces = self.encode_faces(image.get())
face = encoded_faces[0]
log.debug(f'found face: {face}')
all_encodings = self.__db.get_all_encodings(self.__max_workers)
res = [r for r in self.__executor.map(
self.__encoder.distance,
all_encodings[0],
itertools.repeat(face['encoding']))]
distances = numpy.concatenate(res)
filtered = []
for dist, info in zip(distances, all_encodings[1]):
if dist < 0.4:
filtered.append((dist, info))
filtered.sort()
log.debug(f'{len(filtered)} faces matched')
self.__start_stage(len(filtered))
for dist, info in filtered:
if self.__step_stage():
break
fname, face = info
face['dist'] = dist
media = tools.load_media(fname,
self.__max_size,
self.__max_video_frames,
self.__video_frames_step)
debug_out_file_name = self.__extract_filename(fname)
self.__save_debug_images(
(face,), media,
debug_out_folder, debug_out_file_name)
self.__step_stage_face()
if remove_file:
log.debug(f'removing temp file: {filename}')
os.remove(filename)
def __match_files_faces(
self, files_faces, debug_out_folder,
save_all_faces=False, skip_face_gen=False):
cnt_all = 0
cnt_changed = 0
for ff in files_faces:
if self.__step_stage():
break
filename = ff['filename']
log.info(f"match image: {filename}")
is_video = tools.get_low_ext(filename) in tools.VIDEO_EXTS
if not self.__match_faces(ff['faces']):
continue
for face in ff['faces']:
if self.__step_stage_face():
break
cnt_all += 1
changed = False
if 'oldname' in face and face['oldname'] != face['name']:
self.__db.set_name(face['face_id'], face['name'],
face['dist'], face['pattern'],
commit=False)
cnt_changed += 1
changed = True
log.info(
f"face {face['face_id']} in file '{ff['filename']}' " +
f"changed '{face['oldname']}' -> '{face['name']}'")
if debug_out_folder and (changed or save_all_faces):
media = tools.load_media(filename,
self.__max_size,
self.__max_video_frames,
self.__video_frames_step)
debug_out_file_name = self.__extract_filename(filename)
self.__save_debug_images(
(face,), media,
debug_out_folder, debug_out_file_name,
is_video=is_video,
skip_face_gen=skip_face_gen)
self.__end_stage()
log.info(f'match done: count: {cnt_all}, changed: {cnt_changed}')
